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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amps
    -0.07
     blades
    -0.07
    [z
    -0.06
    ype
    -0.06
    들이
    -0.06
    χ
    -0.06
    Gary
    -0.06
    杜
    -0.06
    uckets
    -0.06
     accustomed
    -0.06
    POSITIVE LOGITS
     μία
    0.07
    );}
    0.07
     tě
    0.07
     strive
    0.06
    excerpt
    0.06
     Sculpt
    0.06
     робота
    0.06
     States
    0.06
    _EXIT
    0.06
     Broadcom
    0.06
    Act Density 0.013%

    No Known Activations