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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fragrance
    -0.06
    (parts
    -0.06
    076
    -0.06
     отношения
    -0.06
    365
    -0.06
     unlucky
    -0.06
    .UltraWin
    -0.06
    reasonable
    -0.06
     incorporation
    -0.06
     Kind
    -0.06
    POSITIVE LOGITS
    shan
    0.07
     VR
    0.07
    web
    0.07
    CREATE
    0.07
     SEM
    0.07
     STE
    0.07
    BOR
    0.06
    ahu
    0.06
    ороз
    0.06
    وج
    0.06
    Act Density 0.175%

    No Known Activations