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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =(
    -0.07
    customers
    -0.07
     mirrors
    -0.07
    _html
    -0.06
    Builders
    -0.06
    řit
    -0.06
    _DM
    -0.06
     clashes
    -0.06
     μπο
    -0.06
     :(
    -0.06
    POSITIVE LOGITS
     (**
    0.07
    ोह
    0.06
     Làm
    0.06
    _ALLOW
    0.06
    '''↵
    0.06
     crossAxisAlignment
    0.06
     شرح
    0.06
    ">${
    0.06
     primaryStage
    0.06
    及其
    0.06
    Act Density 0.000%

    No Known Activations