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

    Neuronpedia

    INDEX
    Explanations

    Grammar and verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    UDP
    -0.07
    Rent
    -0.07
    业
    -0.06
    ání
    -0.06
    Congratulations
    -0.06
    _launch
    -0.06
     vigil
    -0.06
    interpret
    -0.06
     hooks
    -0.06
    POSITIVE LOGITS
    .comm
    0.08
    course
    0.06
     PATH
    0.06
    larıyla
    0.06
     Revolutionary
    0.06
     최신
    0.06
     Zhang
    0.06
    -haspopup
    0.06
     кому
    0.06
    oze
    0.06
    Act Density 0.005%

    No Known Activations