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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     developed
    -0.07
    销
    -0.07
    רעיונות
    -0.06
    消費者
    -0.06
    IDX
    -0.06
     existential
    -0.06
     Kann
    -0.06
    omain
    -0.06
     Fetish
    -0.06
    注销
    -0.06
    POSITIVE LOGITS
    选股
    0.07
    侣
    0.07
     política
    0.07
    .sem
    0.07
    :before
    0.06
    领
    0.06
    ridged
    0.06
     руб
    0.06
    (results
    0.06
     nya
    0.06
    Act Density 0.134%

    No Known Activations