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

    Neuronpedia

    INDEX
    Explanations

    academic, scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASSWORD
    -0.07
    trie
    -0.07
     probabilities
    -0.07
     оз
    -0.07
    VERY
    -0.06
     brit
    -0.06
     bending
    -0.06
     prisons
    -0.06
    663
    -0.06
     blocks
    -0.06
    POSITIVE LOGITS
    omap
    0.08
    arm
    0.07
    pu
    0.06
     semiclass
    0.06
    _LIB
    0.06
    ezpe
    0.06
     인간
    0.06
     accession
    0.06
     hạ
    0.06
     çalışma
    0.06
    Act Density 0.167%

    No Known Activations