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

    Neuronpedia

    INDEX
    Explanations

    divisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erez
    -0.07
    铻
    -0.07
    מז
    -0.07
    いず
    -0.07
    調べ
    -0.07
     Sz
    -0.07
    beros
    -0.06
    /arm
    -0.06
    じ
    -0.06
     już
    -0.06
    POSITIVE LOGITS
     Wave
    0.07
     sexually
    0.07
     Structural
    0.07
    BL
    0.07
     Domestic
    0.07
    Dom
    0.07
    Cheap
    0.06
     Antarctic
    0.06
     Package
    0.06
     Messages
    0.06
    Act Density 0.096%

    No Known Activations