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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valeurs
    -0.06
    OLEAN
    -0.06
     se
    -0.06
     Se
    -0.06
    .ADMIN
    -0.06
    oir
    -0.06
    وی
    -0.06
    secret
    -0.06
    unting
    -0.06
    芙
    -0.05
    POSITIVE LOGITS
    vature
    0.07
    Added
    0.07
    集
    0.07
     Same
    0.06
     graf
    0.06
    <Client
    0.06
    Keyboard
    0.06
     embroid
    0.06
     lava
    0.06
    BA
    0.06
    Act Density 0.018%

    No Known Activations