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

    Neuronpedia

    INDEX
    Explanations

    converted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     organise
    -0.07
     Hir
    -0.06
    PTY
    -0.06
    Bullet
    -0.06
     Cur
    -0.06
     infix
    -0.06
     депут
    -0.06
    학
    -0.06
    éo
    -0.06
     nas
    -0.06
    POSITIVE LOGITS
     μπορεί
    0.06
    ())
↵
    0.06
    ॉन
    0.06
     bounce
    0.06
     जव
    0.06
     transformation
    0.06
     لكل
    0.06
    :"",
    0.06
     ضد
    0.06
     xu
    0.06
    Act Density 0.011%

    No Known Activations