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

    Neuronpedia

    INDEX
    Explanations

    non-trivial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avl
    -0.07
    .Validation
    -0.07
    _encode
    -0.06
    _Offset
    -0.06
     Mara
    -0.06
     slut
    -0.06
     рабо
    -0.06
    .getSession
    -0.06
    horia
    -0.06
    stalk
    -0.06
    POSITIVE LOGITS
    elems
    0.06
     unclear
    0.06
     obvious
    0.06
    sass
    0.06
     clear
    0.06
    est
    0.06
     disappoint
    0.06
     '':↵
    0.06
     (($
    0.06
    Lab
    0.06
    Act Density 0.006%

    No Known Activations