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

    Neuronpedia

    INDEX
    Explanations

    say the ending "tools"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
      
    -0.07
     kw
    -0.06
    _program
    -0.06
     cornerback
    -0.06
     [~,
    -0.06
     fierc
    -0.06
     distinct
    -0.06
    ootball
    -0.06
    *
↵
    -0.06
     Mk
    -0.06
    POSITIVE LOGITS
    _front
    0.06
    ffee
    0.06
     backend
    0.06
     maxY
    0.06
     Fl
    0.06
     DVR
    0.06
     shootout
    0.06
     fich
    0.06
    (serial
    0.05
    ;width
    0.05
    Act Density 0.039%

    No Known Activations