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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    支柱
    -0.07
    ってしま
    -0.07
    っきり
    -0.07
     Account
    -0.07
     contraction
    -0.07
     cramped
    -0.07
    agu
    -0.07
    errupt
    -0.06
     stronę
    -0.06
    拮
    -0.06
    POSITIVE LOGITS
     [`
    0.07
    interpreted
    0.06
    с
    0.06
    床
    0.06
    �
    0.06
    ᚱ
    0.06
    _verts
    0.06
    三亚
    0.06
    娃
    0.06
    沃尔
    0.06
    Act Density 0.050%

    No Known Activations