Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentences that begin with periods or transition phrases indicating a new statement or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    beginning of sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.71
    AccessorTable
    -0.69
    RegressionTest
    -0.65
    SBATCH
    -0.65
    TabIndex
    -0.63
    ResumeLayout
    -0.63
    aarrggbb
    -0.62
     ब्रेकडाउन
    -0.62
     CreateTagHelper
    -0.62
    PerformLayout
    -0.61
    POSITIVE LOGITS
     motyw
    0.33
     emperador
    0.31
     consisting
    0.30
    assertIs
    0.29
    alignSelf
    0.28
     ног
    0.28
    /}.
    0.28
     manifestazione
    0.28
     aims
    0.28
     consists
    0.28
    Act Density 0.115%

    No Known Activations