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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tile
    -0.07
    }`).
    -0.07
    unifu
    -0.07
     Copp
    -0.06
    returned
    -0.06
    .inverse
    -0.06
    меж
    -0.06
    	inter
    -0.06
    nerRadius
    -0.06
     returning
    -0.06
    POSITIVE LOGITS
    VES
    0.07
     marvel
    0.07
    MB
    0.07
    quoi
    0.07
    omination
    0.07
    خم
    0.07
    SHA
    0.07
    дром
    0.06
     veřejné
    0.06
    ी।
    0.06
    Act Density 0.006%

    No Known Activations