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

    Neuronpedia

    INDEX
    Explanations

    math terminology and reasoning.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    theless
    -0.06
    posix
    -0.06
     somehow
    -0.06
    ãģĤãģĴ
    -0.06
    ville
    -0.06
    drv
    -0.06
     ATTRIBUTE
    -0.05
    ensing
    -0.05
    931
    -0.05
    θÎŃ
    -0.05
    POSITIVE LOGITS
     possibly
    0.24
     may
    0.23
     potentially
    0.22
    may
    0.19
    åı¯èĥ½
    0.18
     might
    0.17
    possibly
    0.17
     unless
    0.16
     maybe
    0.15
     likely
    0.15
    Act Density 0.144%

    No Known Activations