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

    Neuronpedia

    INDEX
    Explanations

    ">"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corruption
    -0.07
    	Created
    -0.06
     없었
    -0.06
    jem
    -0.06
    -ajax
    -0.06
    backward
    -0.06
    励
    -0.06
    まる
    -0.06
    Qed
    -0.06
    .flag
    -0.06
    POSITIVE LOGITS
    fine
    0.07
    tout
    0.07
    ля
    0.06
    ally
    0.06
    ask
    0.06
     dua
    0.06
    imately
    0.06
     vál
    0.06
    815
    0.06
     ніч
    0.06
    Act Density 0.001%

    No Known Activations