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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IBUT
    -0.06
    jango
    -0.06
     nome
    -0.06
    -gay
    -0.06
    trib
    -0.06
    (tp
    -0.06
     potion
    -0.06
    pei
    -0.06
     intending
    -0.06
     mean
    -0.06
    POSITIVE LOGITS
     Studio
    0.06
     输
    0.06
    aeper
    0.06
     pedals
    0.06
     onBind
    0.06
     Mistress
    0.06
     가장
    0.06
     есть
    0.06
    》
    0.06
    licted
    0.06
    Act Density 0.238%

    No Known Activations