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

    Neuronpedia

    INDEX
    Explanations

    Amos Moses background blur

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conjectures
    0.41
     অবজারভার
    0.40
    ವರ್
    0.40
    वर्
    0.39
     quoting
    0.39
     Miniature
    0.39
    bracketing
    0.38
    ufieurs
    0.37
    oretto
    0.36
     continuum
    0.36
    POSITIVE LOGITS
    批准
    0.47
    redir
    0.41
    ...">
    0.39
    irst
    0.39
    ‹
    0.39
    ...</
    0.38
    eb
    0.37
    负责
    0.37
    ';"/>
    0.37
    otar
    0.36
    Act Density 0.001%

    No Known Activations