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

    Neuronpedia

    INDEX
    Explanations

    Short length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Threads
    -0.07
     Greek
    -0.07
    ERAL
    -0.07
     progressed
    -0.06
     broth
    -0.06
    ğına
    -0.06
     Thursday
    -0.06
    ツ
    -0.06
    Further
    -0.06
    잖
    -0.06
    POSITIVE LOGITS
     جریان
    0.07
    _party
    0.07
    ahaha
    0.07
     Υπο
    0.06
     aplikace
    0.06
     Sociology
    0.06
    antal
    0.06
    iề
    0.06
    oretical
    0.06
    creature
    0.06
    Act Density 0.118%

    No Known Activations