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
     decreases
    -0.07
    準
    -0.06
    Maps
    -0.06
     placeholder
    -0.06
    (tcp
    -0.06
    そう
    -0.06
    �
    -0.06
     footsteps
    -0.06
    ANTI
    -0.06
    581
    -0.06
    POSITIVE LOGITS
     discipline
    0.06
     intellectuals
    0.06
     canadian
    0.06
    bing
    0.06
    *z
    0.06
     climbing
    0.06
    ications
    0.06
    ív
    0.06
    getInstance
    0.06
     Ging
    0.06
    Act Density 0.000%

    No Known Activations