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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artists
    -0.07
     malicious
    -0.07
    .model
    -0.06
    icio
    -0.06
     att
    -0.06
     터
    -0.06
    Phones
    -0.06
     submarine
    -0.06
    Struct
    -0.06
     peaked
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.08
    -users
    0.07
    oola
    0.06
     prefab
    0.06
     dame
    0.06
    /cal
    0.06
     nutné
    0.06
    成功
    0.06
     {})↵
    0.06
    铺
    0.06
    Act Density 0.022%

    No Known Activations