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

    Neuronpedia

    INDEX
    Explanations

    deli

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.67
    parseColor
    -0.52
    rungsseite
    -0.51
    ｡
    -0.49
    ]")]
    -0.48
    пло
    -0.48
     utafitiHapana
    -0.48
    Autoritní
    -0.48
     typelib
    -0.47
    impulan
    -0.46
    POSITIVE LOGITS
    UnknownFieldSet
    0.50
     pyta
    0.50
    ctu
    0.47
     BorderRadius
    0.47
    ete
    0.46
    qu
    0.46
    ANTLR
    0.46
    vient
    0.45
    atists
    0.45
    ujian
    0.45
    Act Density 0.000%

    No Known Activations