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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .writeFile
    -0.07
     Hanna
    -0.06
     جا
    -0.06
     intim
    -0.06
     NR
    -0.06
     الاتحاد
    -0.06
     ní
    -0.06
    _COLS
    -0.06
     laptop
    -0.06
     Psi
    -0.06
    POSITIVE LOGITS
    .reason
    0.07
    →→
    0.07
    libc
    0.06
     environmentally
    0.06
    igu
    0.06
    robe
    0.06
    uben
    0.06
    _self
    0.06
    odu
    0.06
    -next
    0.06
    Act Density 0.000%

    No Known Activations