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

    Neuronpedia

    INDEX
    Explanations

    greetings and wishes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    팠
    -0.08
    <X
    -0.07
    ifact
    -0.07
    もない
    -0.07
     eldest
    -0.07
     cupboard
    -0.07
    NotEmpty
    -0.07
    (socket
    -0.07
    Outputs
    -0.07
    过错
    -0.07
    POSITIVE LOGITS
    שמירה
    0.07
     Harding
    0.07
    语
    0.07
     giáo
    0.07
    Edited
    0.07
    BackColor
    0.07
    Vir
    0.07
    [iVar
    0.07
     word
    0.07
     Myers
    0.07
    Act Density 0.010%

    No Known Activations