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

    Neuronpedia

    INDEX
    Explanations

    Table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Defined
    -0.07
    Univers
    -0.07
    алення
    -0.07
     SMB
    -0.07
    ενοδο
    -0.07
    �
    -0.07
     Cinder
    -0.07
    縣
    -0.07
     theaters
    -0.06
    urger
    -0.06
    POSITIVE LOGITS
    (recv
    0.06
     MIME
    0.06
    _ble
    0.06
    -twitter
    0.06
     الان
    0.06
     WebView
    0.06
    leston
    0.05
    >'.↵
    0.05
    crypto
    0.05
    .Copy
    0.05
    Act Density 0.003%

    No Known Activations