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

    Neuronpedia

    INDEX
    Explanations

    writing creative descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hospice
    -0.08
    ldb
    -0.08
    ක්
    -0.08
     ie
    -0.08
    lex
    -0.07
    胞
    -0.07
     Concept
    -0.07
     Examine
    -0.07
     Inputs
    -0.07
    ෙක්
    -0.07
    POSITIVE LOGITS
    .↵↵↵↵
    0.09
    。↵↵↵↵
    0.08
    ."
    0.08
    Peso
    0.08
    Packed
    0.08
     cohes
    0.07
     distorted
    0.07
     cuc
    0.07
     وإ
    0.07
    ?↵↵↵↵
    0.07
    Act Density 0.066%

    No Known Activations