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

    Neuronpedia

    INDEX
    Explanations

    code diff lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    カスタ
    0.41
    ulik
    0.38
     ustan
    0.38
     Ein
    0.36
    nici
    0.36
    insta
    0.35
    собенно
    0.34
     pyroph
    0.34
     oxígeno
    0.33
    icka
    0.33
    POSITIVE LOGITS
    ৫
    0.40
    7
    0.39
    Reads
    0.38
    6
    0.36
     ৭
    0.35
    maso
    0.35
     profile
    0.34
    +\
    0.34
    ásra
    0.33
    ৮
    0.33
    Act Density 0.000%

    No Known Activations