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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Flags
    -0.07
    мор
    -0.07
     ци
    -0.06
    enced
    -0.06
     ima
    -0.06
     bum
    -0.06
     Hou
    -0.06
    oğun
    -0.06
    AMA
    -0.06
    icine
    -0.06
    POSITIVE LOGITS
     allowNull
    0.07
    ories
    0.07
     React
    0.07
     twink
    0.06
     употреб
    0.06
    -auth
    0.06
     Methods
    0.06
    -answer
    0.06
     joueur
    0.06
    มหาว
    0.06
    Act Density 0.085%

    No Known Activations