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

    Neuronpedia

    INDEX
    Explanations

    code/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    র্�
    -0.08
     қор
    -0.08
    קען
    -0.08
    ুক্ত
    -0.08
    ーカー
    -0.07
    പ്പോൾ
    -0.07
    izando
    -0.07
    onomia
    -0.07
    हेका
    -0.07
    tributing
    -0.07
    POSITIVE LOGITS
     autof
    0.08
     woven
    0.08
    ,length
    0.08
    ulong
    0.08
    jmp
    0.07
    tw
    0.07
     redraw
    0.07
     género
    0.07
    autos
    0.07
     جس
    0.07
    Act Density 0.000%

    No Known Activations