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

    Neuronpedia

    INDEX
    Explanations

    ter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cls
    -0.06
     thief
    -0.06
    Curve
    -0.06
    ?=
    -0.06
    tmpl
    -0.06
     форме
    -0.06
     tough
    -0.06
    _smooth
    -0.06
     ho
    -0.06
     leuk
    -0.06
    POSITIVE LOGITS
    ılacak
    0.08
     repent
    0.07
     náv
    0.07
     отлич
    0.07
    reesome
    0.06
     esk
    0.06
    unication
    0.06
    strcpy
    0.06
    ламент
    0.06
     assum
    0.06
    Act Density 0.151%

    No Known Activations