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

    Neuronpedia

    INDEX
    Explanations

    home services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Studios
    -0.08
     Fight
    -0.07
     Trick
    -0.07
     Shir
    -0.07
     Blog
    -0.07
    STOP
    -0.07
     ngu
    -0.07
    وس
    -0.07
     HOUR
    -0.06
    estring
    -0.06
    POSITIVE LOGITS
    _company
    0.06
    主義
    0.06
    š
    0.06
     awarded
    0.06
     ensuing
    0.06
    звичай
    0.06
     reelection
    0.06
    وجود
    0.06
    addChild
    0.05
     immutable
    0.05
    Act Density 0.180%

    No Known Activations