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

    Neuronpedia

    INDEX
    Explanations

    adjustable devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Add
    -0.07
     Blank
    -0.07
    Spin
    -0.07
    fern
    -0.07
     Ahmad
    -0.07
     salads
    -0.07
    -around
    -0.07
    �
    -0.06
     lunches
    -0.06
     Tax
    -0.06
    POSITIVE LOGITS
    (Member
    0.06
     fucked
    0.06
    _Master
    0.06
     σαν
    0.06
    ';↵↵↵
    0.06
    CLUD
    0.06
    "H
    0.06
     ат
    0.06
    verbs
    0.06
    (Function
    0.05
    Act Density 0.056%

    No Known Activations