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
    MeshPro
    -0.08
     rou
    -0.08
     boys
    -0.07
     Cara
    -0.07
     Cyril
    -0.07
     dun
    -0.07
     citation
    -0.07
     Sand
    -0.07
    _SYM
    -0.07
     ground
    -0.07
    POSITIVE LOGITS
    雳
    0.08
    Variant
    0.07
    �
    0.07
    보다
    0.07
    opause
    0.07
    より
    0.07
    ologie
    0.07
    耳机
    0.07
    فض
    0.07
     Trước
    0.06
    Act Density 0.002%

    No Known Activations