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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rem
    -0.07
     slate
    -0.06
     dzieci
    -0.06
    Como
    -0.06
    English
    -0.06
     dabei
    -0.06
    -century
    -0.06
    ry
    -0.06
    bij
    -0.06
     English
    -0.06
    POSITIVE LOGITS
    프로
    0.08
    HOST
    0.07
     προς
    0.07
    _COPY
    0.06
     ممن
    0.06
    _HTTP
    0.06
    .LEFT
    0.06
     ￣
    0.06
     casc
    0.06
     Ukra
    0.06
    Act Density 0.064%

    No Known Activations