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

    Neuronpedia

    INDEX
    Explanations

    Helping Verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .real
    -0.06
     ==
    -0.06
    hv
    -0.06
    STRUCTIONS
    -0.06
     SES
    -0.06
    urile
    -0.06
     ข
    -0.06
    -k
    -0.06
    _UDP
    -0.06
    _detach
    -0.06
    POSITIVE LOGITS
     وش
    0.07
     theoretically
    0.06
    iesz
    0.06
    Column
    0.06
    см
    0.06
    abilirsiniz
    0.06
     İnsan
    0.06
    opus
    0.06
    irts
    0.06
    ls
    0.06
    Act Density 0.055%

    No Known Activations