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
    实验室
    -0.07
     setValue
    -0.07
     Fortune
    -0.07
    .release
    -0.07
     acquiring
    -0.07
    cluir
    -0.07
     اللجنة
    -0.06
     scored
    -0.06
    .DataAccess
    -0.06
    指责
    -0.06
    POSITIVE LOGITS
    饮料
    0.08
    百科
    0.08
    甩
    0.07
    cw
    0.07
    能够在
    0.07
     shorter
    0.06
     cedar
    0.06
     Snow
    0.06
    -br
    0.06
    干旱
    0.06
    Act Density 0.012%

    No Known Activations