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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <=(
    -0.07
    ्पष
    -0.06
     jer
    -0.06
    }><
    -0.06
    开发
    -0.06
    _saved
    -0.06
    WRITE
    -0.06
     트
    -0.06
     �
    -0.06
     vyjád
    -0.06
    POSITIVE LOGITS
     McKenzie
    0.08
     terminology
    0.07
    Bush
    0.07
    lage
    0.06
     jurors
    0.06
    …………………………………………
    0.06
    (bits
    0.06
    quette
    0.06
    prints
    0.06
     ballistic
    0.06
    Act Density 0.045%

    No Known Activations