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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     behest
    1.44
     ADHD
    1.42
     PvP
    1.39
     HPV
    1.38
     neoliberal
    1.37
     ballads
    1.37
     epistem
    1.37
     burgeoning
    1.37
     revital
    1.35
     LEGO
    1.33
    POSITIVE LOGITS
    //
    2.79
    if
    2.37
    return
    2.27
    try
    2.26
    print
    2.01
    #
    1.97
    for
    1.76
    while
    1.74
    assert
    1.74
    var
    1.72
    Act Density 0.537%

    No Known Activations