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

    Neuronpedia

    INDEX
    Explanations

    Code syntaxes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .other
    -0.08
     hires
    -0.07
     deutschen
    -0.07
    ']↵↵↵
    -0.07
     advises
    -0.07
    .Series
    -0.06
    gr
    -0.06
     criter
    -0.06
     briefed
    -0.06
    !"
    -0.06
    POSITIVE LOGITS
     Наз
    0.07
    ιας
    0.07
    ANCES
    0.06
    GetType
    0.06
     quoi
    0.06
    orial
    0.06
    -th
    0.06
     henne
    0.06
     Sleeve
    0.06
    س
    0.06
    Act Density 0.014%

    No Known Activations