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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (circle
    -0.06
    Sessions
    -0.06
    apor
    -0.06
    üzel
    -0.06
    їх
    -0.06
    사이
    -0.06
     selection
    -0.06
    zilla
    -0.06
     allocations
    -0.06
     choice
    -0.06
    POSITIVE LOGITS
     мож
    0.08
    _Trans
    0.07
     UserType
    0.07
    _LP
    0.07
     §§
    0.07
     Eth
    0.07
     FUCK
    0.07
     یوتی
    0.07
    -hash
    0.06
    :any
    0.06
    Act Density 0.001%

    No Known Activations