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

    Neuronpedia

    INDEX
    Explanations

    Dimensions (Height and Width)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scary
    -0.08
     Radi
    -0.07
    yte
    -0.06
     Archae
    -0.06
    atics
    -0.06
    (space
    -0.06
    Ast
    -0.06
    _exchange
    -0.06
    stem
    -0.06
    Rob
    -0.06
    POSITIVE LOGITS
    912
    0.06
    ediální
    0.06
    jandro
    0.06
    918
    0.06
    ो।
    0.06
    HomeAsUpEnabled
    0.06
     frost
    0.06
    93
    0.06
     حاضر
    0.06
    яж
    0.06
    Act Density 0.019%

    No Known Activations