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

    Neuronpedia

    INDEX
    Explanations

    Common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weapons
    -0.07
     scalar
    -0.07
     Giáo
    -0.07
     Glory
    -0.06
     Investment
    -0.06
     Benson
    -0.06
    (player
    -0.06
    .account
    -0.06
    arming
    -0.06
    206
    -0.06
    POSITIVE LOGITS
    _intr
    0.07
    _home
    0.07
    _OF
    0.06
     Sud
    0.06
    //↵↵↵
    0.06
     extortion
    0.06
     agreg
    0.06
     overseeing
    0.06
    -direction
    0.06
    EntityManager
    0.06
    Act Density 0.170%

    No Known Activations