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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     슈
    -0.07
    شة
    -0.07
     gå
    -0.07
    uforia
    -0.06
     своим
    -0.06
     кому
    -0.06
     WH
    -0.06
    .Adam
    -0.06
     recebe
    -0.06
     tội
    -0.06
    POSITIVE LOGITS
    oving
    0.07
    olved
    0.07
    MethodImpl
    0.06
     žalob
    0.06
    -character
    0.06
    cancelled
    0.06
     performs
    0.06
    instrument
    0.06
     Operational
    0.06
    oval
    0.06
    Act Density 0.000%

    No Known Activations