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

    Neuronpedia

    INDEX
    Explanations

    Go Daddy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     воспомина
    0.36
    见的
    0.35
     ምስ
    0.34
     postice
    0.34
     strCmd
    0.33
    நாயக
    0.33
    მარ
    0.33
    笵
    0.32
     sostit
    0.32
     SUBSTITUTE
    0.32
    POSITIVE LOGITS
     ahead
    0.57
    ahead
    0.55
    Ahead
    0.49
     Ahead
    0.46
     onward
    0.39
    arant
    0.38
    along
    0.37
     forward
    0.36
     crazy
    0.36
     along
    0.35
    Act Density 0.005%

    No Known Activations