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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    677
    -0.07
     matte
    -0.07
     ic
    -0.06
     LIGHT
    -0.06
    "]}↵
    -0.06
     IAM
    -0.06
    598
    -0.06
     herd
    -0.06
     rfl
    -0.06
     hrs
    -0.06
    POSITIVE LOGITS
    альної
    0.07
    isodes
    0.06
    ぶ
    0.06
    .folder
    0.06
    mal
    0.06
     proprio
    0.06
     міг
    0.06
    وال
    0.06
     heirs
    0.06
    RunWith
    0.06
    Act Density 0.012%

    No Known Activations