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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    company
    -0.07
     metal
    -0.07
     Metal
    -0.06
    ithub
    -0.06
     gösterir
    -0.06
    Keyboard
    -0.06
    ังคม
    -0.06
    지만
    -0.06
    WITH
    -0.06
    訂
    -0.06
    POSITIVE LOGITS
    _pes
    0.07
     spreading
    0.07
    (iterator
    0.06
     SAY
    0.06
     nip
    0.06
     testament
    0.06
     χρό
    0.06
    _POINTER
    0.06
     globally
    0.06
     Joseph
    0.06
    Act Density 0.003%

    No Known Activations