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

    Neuronpedia

    INDEX
    Explanations

    job

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    internal
    -0.07
    	UINT
    -0.07
    _Final
    -0.07
    URAL
    -0.06
     Ville
    -0.06
     glam
    -0.06
    (double
    -0.06
     회원
    -0.06
    れる
    -0.06
    dae
    -0.06
    POSITIVE LOGITS
     sil
    0.07
    链
    0.06
    pointer
    0.06
     Γεω
    0.06
     addChild
    0.06
    .After
    0.06
    _subscribe
    0.06
    клад
    0.06
     нада
    0.06
    HEY
    0.06
    Act Density 0.024%

    No Known Activations