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

    Neuronpedia

    INDEX
    Explanations

    suspicion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    washer
    -0.06
     mục
    -0.06
     июля
    -0.06
     optim
    -0.06
    ิ่
    -0.06
     raping
    -0.06
    Versions
    -0.06
    estar
    -0.06
    clair
    -0.06
    ussed
    -0.06
    POSITIVE LOGITS
     Config
    0.07
    poser
    0.06
     Sous
    0.06
    					
↵
    0.06
    _pose
    0.06
     Mount
    0.06
    ط
    0.06
     sv
    0.06
     شود
    0.06
     Liv
    0.06
    Act Density 0.021%

    No Known Activations