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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Approach
    -0.07
    .getLong
    -0.06
     hundred
    -0.06
    >';
    -0.06
     Jessie
    -0.06
    .`,↵
    -0.06
     puck
    -0.06
     millennials
    -0.06
     Reload
    -0.06
    _PARENT
    -0.06
    POSITIVE LOGITS
    CNT
    0.07
    borough
    0.06
    igin
    0.06
    lean
    0.06
     Dropbox
    0.06
    <source
    0.06
     rejection
    0.06
     rigid
    0.06
    toInt
    0.06
    arching
    0.06
    Act Density 0.027%

    No Known Activations