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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Islanders
    -0.07
     Deutsche
    -0.07
     pełne
    -0.07
    orphic
    -0.07
    itious
    -0.07
    陈列
    -0.06
    .UserInfo
    -0.06
     RouterModule
    -0.06
     Evelyn
    -0.06
     clientele
    -0.06
    POSITIVE LOGITS
     Greenwood
    0.07
     Draw
    0.07
    昊
    0.07
     Psycho
    0.07
     Pra
    0.06
     pwd
    0.06
     suicide
    0.06
    си
    0.06
     Warsaw
    0.06
    코
    0.06
    Act Density 0.078%

    No Known Activations