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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    項目
    -0.07
    _PD
    -0.07
    ctype
    -0.07
     firsthand
    -0.07
     palindrome
    -0.06
     Tato
    -0.06
     Byte
    -0.06
     díky
    -0.06
     Poverty
    -0.06
     Successfully
    -0.06
    POSITIVE LOGITS
     assemble
    0.07
    .tax
    0.07
     FAG
    0.07
    ,assign
    0.06
    Derived
    0.06
    _saved
    0.06
     social
    0.06
     *);↵↵
    0.06
     claimed
    0.06
     предвар
    0.06
    Act Density 0.274%

    No Known Activations