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

    Neuronpedia

    INDEX
    Explanations

    technical documentation, captions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    届
    -0.07
     flashed
    -0.07
    CONN
    -0.07
    _edges
    -0.07
    .identity
    -0.07
     робіт
    -0.06
     changed
    -0.06
    くな
    -0.06
     Yao
    -0.06
     included
    -0.06
    POSITIVE LOGITS
     massa
    0.07
     вред
    0.07
    SEE
    0.06
     �
    0.06
    mpar
    0.06
    /trunk
    0.06
     rooft
    0.06
     herkes
    0.06
    (lines
    0.06
     бума
    0.06
    Act Density 0.000%

    No Known Activations