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

    Neuronpedia

    INDEX
    Explanations

    Code or math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plan
    -0.07
    amping
    -0.07
     minutos
    -0.07
    Disk
    -0.06
    SAFE
    -0.06
     Cheng
    -0.06
    CEO
    -0.06
    异常
    -0.06
    Delete
    -0.06
    goods
    -0.06
    POSITIVE LOGITS
    ุดท
    0.07
    rina
    0.07
    (enable
    0.07
     ﾉ
    0.06
     inex
    0.06
    ashion
    0.06
     Akron
    0.06
     goalkeeper
    0.06
     forward
    0.06
    γού
    0.06
    Act Density 0.126%

    No Known Activations