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

    Neuronpedia

    INDEX
    Explanations

    /bin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ghost
    -0.08
     películ
    -0.07
    iego
    -0.07
     talks
    -0.06
    値
    -0.06
    fallback
    -0.06
     Made
    -0.06
     celebrity
    -0.06
    (guess
    -0.06
     grande
    -0.06
    POSITIVE LOGITS
     DIN
    0.08
    \x
    0.07
    /pi
    0.07
    /bin
    0.07
    -training
    0.06
    MethodImpl
    0.06
    encodeURIComponent
    0.06
     нали
    0.06
     LEN
    0.06
     han
    0.06
    Act Density 0.003%

    No Known Activations