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

    Neuronpedia

    INDEX
    Explanations

    pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .writeInt
    -0.07
    .mob
    -0.07
    .coll
    -0.07
    .OUT
    -0.06
    |max
    -0.06
     tamil
    -0.06
     useState
    -0.06
     Signs
    -0.06
    .tv
    -0.06
     תא
    -0.06
    POSITIVE LOGITS
    стью
    0.08
    💕
    0.07
     preca
    0.07
    ـ
    0.07
     jazz
    0.06
     aj
    0.06
    gium
    0.06
     gratuita
    0.06
     Brandon
    0.06
    窀
    0.06
    Act Density 0.017%

    No Known Activations