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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paths
    -0.07
     types
    -0.07
    东西
    -0.06
     Belgium
    -0.06
    =float
    -0.06
     phone
    -0.06
    .Drop
    -0.06
    افته
    -0.06
     advancing
    -0.06
     environments
    -0.06
    POSITIVE LOGITS
    equalsIgnoreCase
    0.07
    _weak
    0.07
     väl
    0.06
     Prem
    0.06
    _OK
    0.06
    _coordinate
    0.06
    oreach
    0.06
     जर
    0.06
    اخر
    0.06
     Ful
    0.06
    Act Density 0.006%

    No Known Activations