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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exhaust
    -0.07
     Rotate
    -0.06
     tính
    -0.06
     CHUNK
    -0.06
     Pig
    -0.06
    _names
    -0.06
    onta
    -0.06
    ary
    -0.06
     assays
    -0.06
    reme
    -0.06
    POSITIVE LOGITS
     petitioner
    0.07
    0.07
    )V
    0.07
     infer
    0.07
    .additional
    0.06
     내려
    0.06
     कर
    0.06
    /repos
    0.06
    込み
    0.06
    (speed
    0.06
    Act Density 0.003%

    No Known Activations