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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IOC
    -0.08
    .ro
    -0.06
    poi
    -0.06
     toy
    -0.06
     Neutral
    -0.06
    belt
    -0.06
    clare
    -0.06
    030
    -0.06
    068
    -0.06
     toys
    -0.06
    POSITIVE LOGITS
     }}>
    0.07
    FieldValue
    0.07
    ْح
    0.07
    (...)↵
    0.07
    iling
    0.06
    EEK
    0.06
     hath
    0.06
    PECT
    0.06
    ınızda
    0.06
    eresa
    0.06
    Act Density 0.007%

    No Known Activations