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

    Neuronpedia

    INDEX
    Explanations

    adequate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /sp
    -0.08
    Person
    -0.07
    (b
    -0.07
    oren
    -0.07
    anlar
    -0.06
    cakes
    -0.06
    .lift
    -0.06
    Provider
    -0.06
     Person
    -0.06
    OB
    -0.06
    POSITIVE LOGITS
    Hola
    0.07
    diği
    0.07
    тє
    0.06
    	onClick
    0.06
    erosis
    0.06
    =session
    0.06
     Sokol
    0.06
    SCRIPT
    0.06
    896
    0.06
     função
    0.06
    Act Density 0.005%

    No Known Activations