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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mul
    -0.08
     Floral
    -0.07
    _malloc
    -0.07
     disgusted
    -0.07
    asterxml
    -0.07
     brun
    -0.07
    骐
    -0.07
    zeitig
    -0.06
    zeigen
    -0.06
     Trees
    -0.06
    POSITIVE LOGITS
    &w
    0.08
    璀
    0.07
    首创
    0.07
    霉素
    0.07
     العملية
    0.07
     "${
    0.07
    >{@
    0.06
    ilestone
    0.06
    쳤
    0.06
    .Event
    0.06
    Act Density 0.002%

    No Known Activations