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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _without
    -0.06
     توق
    -0.06
    /browse
    -0.06
    %)↵
    -0.06
     bekom
    -0.06
    Modificar
    -0.06
    小时
    -0.06
    -Aug
    -0.06
    icie
    -0.06
    -method
    -0.06
    POSITIVE LOGITS
     Counsel
    0.07
     adolescence
    0.07
    妃
    0.07
    (database
    0.06
    perms
    0.06
     counsel
    0.06
     dalších
    0.06
     collaborated
    0.06
    (base
    0.06
    CID
    0.06
    Act Density 0.006%

    No Known Activations