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

    Neuronpedia

    INDEX
    Explanations

    Emails and news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quet
    -0.07
    續
    -0.07
     sale
    -0.07
    ानव
    -0.07
     ikke
    -0.06
     entire
    -0.06
    ки
    -0.06
    Linear
    -0.06
     jehož
    -0.06
    _sources
    -0.06
    POSITIVE LOGITS
    �
    0.07
     ovarian
    0.06
    .Import
    0.06
     gardening
    0.06
     neutron
    0.06
    wrapper
    0.06
    dın
    0.06
     dysfunctional
    0.06
    ılıyor
    0.06
     backstory
    0.06
    Act Density 0.000%

    No Known Activations