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

    Neuronpedia

    INDEX
    Explanations

    steps in a process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↑
    -0.08
    慌
    -0.07
    [property
    -0.07
    №
    -0.07
    Go
    -0.06
     данной
    -0.06
     insol
    -0.06
    矾
    -0.06
    所在
    -0.06
     Spinner
    -0.06
    POSITIVE LOGITS
     RCS
    0.07
    _MARKER
    0.07
     nginx
    0.07
    MERCHANTABILITY
    0.06
    قا
    0.06
    _consts
    0.06
    牵手
    0.06
     Prot
    0.06
     bụ
    0.06
    Yu
    0.06
    Act Density 0.143%

    No Known Activations