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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marry
    -0.07
     traders
    -0.07
     bara
    -0.07
     covariance
    -0.06
     loudly
    -0.06
    و
    -0.06
    enia
    -0.06
     literals
    -0.06
    Teen
    -0.06
    kv
    -0.06
    POSITIVE LOGITS
     '\
    0.07
    �
    0.07
    (icon
    0.07
     زندگی
    0.06
     RECEIVER
    0.06
    _UTF
    0.06
     "\
    0.06
     PROVID
    0.06
    IVITY
    0.06
    Login
    0.06
    Act Density 0.029%

    No Known Activations