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

    Neuronpedia

    INDEX
    Explanations

    existence and confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     속에
    0.39
     должно
    0.38
     len
    0.36
     frag
    0.36
     воде
    0.36
     optimise
    0.36
     achieved
    0.36
     Achieve
    0.35
     లక్ష
    0.35
     odlič
    0.35
    POSITIVE LOGITS
    @-
    0.47
     Motorcycle
    0.41
    copter
    0.40
    Mountain
    0.40
    兗
    0.39
     alcoved
    0.38
    ranger
    0.38
     montrent
    0.38
     Wallet
    0.38
     মার্চের
    0.37
    Act Density 0.000%

    No Known Activations