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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sources
    -0.07
     findings
    -0.07
    见
    -0.06
    EI
    -0.06
     PURE
    -0.06
    .IsNull
    -0.06
    _fore
    -0.06
    cury
    -0.06
     유형
    -0.06
    rant
    -0.06
    POSITIVE LOGITS
     Warm
    0.07
     misses
    0.07
     mekt
    0.06
    (Function
    0.06
     direccion
    0.06
     Cooking
    0.06
    #import
    0.06
    /fonts
    0.06
     pours
    0.06
     Shoes
    0.06
    Act Density 0.004%

    No Known Activations