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
    	n
    -0.07
    pec
    -0.07
    .linkedin
    -0.06
     BER
    -0.06
     elites
    -0.06
    กระแส
    -0.06
    (chat
    -0.06
     borne
    -0.06
     fon
    -0.06
    _FAILED
    -0.06
    POSITIVE LOGITS
    と共
    0.08
     pantry
    0.07
    だと思う
    0.07
    だと
    0.07
    .Can
    0.06
    尽
    0.06
    =#
    0.06
    禁
    0.06
    ⟾
    0.06
    的东西
    0.06
    Act Density 0.002%

    No Known Activations