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
     �
    -0.07
    /Search
    -0.07
     Затем
    -0.06
     robbery
    -0.06
    lein
    -0.06
     bracket
    -0.06
    (ra
    -0.06
    Story
    -0.06
    °С
    -0.06
    Focus
    -0.06
    POSITIVE LOGITS
    default
    0.07
    Available
    0.07
     spoken
    0.07
    ایل
    0.06
    PUT
    0.06
     Çağ
    0.06
     Bedroom
    0.06
     mio
    0.06
    android
    0.06
     hexadecimal
    0.06
    Act Density 0.031%

    No Known Activations