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

    Neuronpedia

    INDEX
    Explanations

    prevention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    evento
    -0.07
    .DropDownStyle
    -0.07
    Happy
    -0.06
     xcb
    -0.06
     favourable
    -0.06
     Favorite
    -0.06
    Class
    -0.06
    -compatible
    -0.06
    orb
    -0.06
     ALIGN
    -0.06
    POSITIVE LOGITS
     prevention
    0.28
     Prevention
    0.22
    vention
    0.10
    ervation
    0.07
     Piper
    0.07
    ンド
    0.07
    동안
    0.07
     scams
    0.07
     inference
    0.07
    iginal
    0.06
    Act Density 0.003%

    No Known Activations