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

    Neuronpedia

    INDEX
    Explanations

    software descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Accordion
    -0.07
    �
    -0.07
    .Meta
    -0.07
     Anne
    -0.07
    .atan
    -0.07
     метал
    -0.07
    사이
    -0.07
    对着
    -0.07
     precursor
    -0.07
    娶
    -0.06
    POSITIVE LOGITS
     personalized
    0.07
    lict
    0.07
    切实
    0.07
    ないと
    0.07
     elimination
    0.06
    blocking
    0.06
    ਆ
    0.06
    觿
    0.06
     nécessaire
    0.06
    .root
    0.06
    Act Density 0.024%

    No Known Activations