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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .span
    -0.07
    TLS
    -0.07
     scé
    -0.07
     cork
    -0.07
     tokenizer
    -0.07
    UMP
    -0.07
    ologue
    -0.06
     kvm
    -0.06
    ;"></
    -0.06
     draining
    -0.06
    POSITIVE LOGITS
    Video
    0.06
    Online
    0.06
     disappoint
    0.06
    Moder
    0.06
    *sizeof
    0.06
     Rebel
    0.06
    ps
    0.06
    Direct
    0.06
    -c
    0.06
     Improved
    0.06
    Act Density 0.038%

    No Known Activations