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

    Neuronpedia

    INDEX
    Explanations

    Personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MAX
    -0.07
     captive
    -0.06
    Plot
    -0.06
    _MIX
    -0.06
    phase
    -0.06
    /my
    -0.06
     част
    -0.06
     Screen
    -0.06
    _screen
    -0.06
     Arcade
    -0.06
    POSITIVE LOGITS
    histoire
    0.07
     якому
    0.07
     ab
    0.07
     Represent
    0.07
     tarihi
    0.06
    gesi
    0.06
    esper
    0.06
     granddaughter
    0.06
    Mel
    0.06
     teammates
    0.06
    Act Density 0.055%

    No Known Activations