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

    Neuronpedia

    INDEX
    Explanations

    uncommon word fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vale
    -0.62
    -0.60
    InvalidProtocol
    -0.58
     DialogInterface
    -0.58
    +#+
    -0.56
    HostException
    -0.56
    ulipas
    -0.55
    Inhalt
    -0.51
    Vale
    -0.51
     Cuisine
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.63
    RefNanny
    0.56
    商品説明
    0.56
     Waray
    0.56
     ar
    0.49
    melada
    0.48
    arnos
    0.48
    Autoritní
    0.48
    Facades
    0.47
    曖昧さ回避
    0.47
    Act Density 0.000%

    No Known Activations