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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Document
    -0.07
     Plant
    -0.07
    Enemy
    -0.06
    	Double
    -0.06
     V
    -0.06
    rio
    -0.06
    307
    -0.06
     PO
    -0.06
    “No
    -0.06
    hev
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ONG
    0.06
    ongs
    0.06
    .Adam
    0.06
     cav
    0.06
     있도록
    0.06
    agedList
    0.06
    .Multiline
    0.06
    YLON
    0.06
    ……………………
    0.06
    Act Density 0.378%

    No Known Activations