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

    Neuronpedia

    INDEX
    Explanations

    findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icult
    -0.07
    =_("
    -0.07
    -cr
    -0.06
     bast
    -0.06
     Marc
    -0.06
    _up
    -0.06
     seul
    -0.06
     _("
    -0.06
    %s
    -0.06
    Ep
    -0.06
    POSITIVE LOGITS
     findings
    0.11
     Watkins
    0.09
     holdings
    0.08
    187
    0.08
    ngör
    0.08
     Rodney
    0.08
    holding
    0.08
     ongoing
    0.07
     eğit
    0.07
     görev
    0.07
    Act Density 0.015%

    No Known Activations