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

    Neuronpedia

    INDEX
    Explanations

    outs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alright
    -0.07
    edriver
    -0.07
     клас
    -0.07
    amoto
    -0.06
    -0.06
    collect
    -0.06
     Certainly
    -0.06
     클래스
    -0.06
    えて
    -0.06
     Garrett
    -0.06
    POSITIVE LOGITS
     �
    0.07
    تغ
    0.07
     unpaid
    0.07
     BSD
    0.06
    .XR
    0.06
    šší
    0.06
     hott
    0.06
    acia
    0.06
    OutOfBounds
    0.06
     Puppy
    0.06
    Act Density 0.003%

    No Known Activations