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

    Neuronpedia

    INDEX
    Explanations

    ?>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     displayed
    -0.07
    茶
    -0.07
    -shaped
    -0.06
     Sunrise
    -0.06
     decipher
    -0.06
    .Tick
    -0.06
    Hat
    -0.06
     rival
    -0.06
     GK
    -0.06
    _bw
    -0.06
    POSITIVE LOGITS
    Ho
    0.06
    ordo
    0.06
    ='/
    0.06
    <AudioSource
    0.06
    kově
    0.06
    aligned
    0.06
    KERNEL
    0.06
     kara
    0.06
    .':
    0.06
    ۶
    0.06
    Act Density 0.000%

    No Known Activations