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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hindu
    -0.06
     Decomp
    -0.06
    Trying
    -0.06
     decreases
    -0.06
     attitude
    -0.06
     엄마
    -0.06
     dinners
    -0.06
     Volley
    -0.06
    ści
    -0.06
     міжнарод
    -0.06
    POSITIVE LOGITS
     activates
    0.06
    :maj
    0.06
     fix
    0.06
     flashed
    0.06
     น
    0.06
    ‐-
    0.06
     zveřej
    0.06
     Crypt
    0.06
     UClass
    0.06
     paddingHorizontal
    0.06
    Act Density 0.286%

    No Known Activations