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

    Neuronpedia

    INDEX
    Explanations

    denied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cracked
    -0.07
     assurance
    -0.06
     fraud
    -0.06
    ad
    -0.06
    Buf
    -0.06
    acciones
    -0.06
    AD
    -0.06
    шее
    -0.06
    `.↵↵
    -0.06
    icerca
    -0.06
    POSITIVE LOGITS
    (APP
    0.07
     trú
    0.07
     waterproof
    0.07
    \F
    0.07
     кажд
    0.07
    /exp
    0.06
     الان
    0.06
    ホ
    0.06
    Terminate
    0.06
     yasal
    0.06
    Act Density 0.007%

    No Known Activations