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

    Neuronpedia

    INDEX
    Explanations

    humans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èo
    -0.07
    арів
    -0.07
     transmitted
    -0.07
    πτωση
    -0.07
     older
    -0.06
    ّر
    -0.06
    ξης
    -0.06
    .compose
    -0.06
     صاح
    -0.06
    _WRAP
    -0.06
    POSITIVE LOGITS
     kar
    0.07
     forgiveness
    0.06
     Sampler
    0.06
    .blank
    0.06
     divisions
    0.06
     �
    0.06
     (*)
    0.06
     win
    0.06
     mixed
    0.06
     concentr
    0.06
    Act Density 0.011%

    No Known Activations