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

    Neuronpedia

    INDEX
    Explanations

    scientific/medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     algebra
    -0.07
    _STRUCT
    -0.06
     repeatedly
    -0.06
    нич
    -0.06
    ############################################################################
    -0.06
     predictions
    -0.06
    invoice
    -0.06
     subtraction
    -0.06
     Satan
    -0.06
    .theme
    -0.06
    POSITIVE LOGITS
    oulos
    0.07
    >Action
    0.06
     inhabit
    0.06
    outcome
    0.06
     lỗi
    0.06
     selects
    0.06
    ESS
    0.06
     phổ
    0.06
    ='_
    0.05
     삼
    0.05
    Act Density 0.094%

    No Known Activations