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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tempting
    -0.07
     attacks
    -0.07
     hành
    -0.06
     पड
    -0.06
     previous
    -0.06
    eket
    -0.06
    番
    -0.06
    یه
    -0.06
    只
    -0.06
     riches
    -0.06
    POSITIVE LOGITS
     jq
    0.07
    _succ
    0.06
     unmist
    0.06
     внутр
    0.06
     começ
    0.06
     схем
    0.06
    onia
    0.06
     onNext
    0.06
     mxArray
    0.06
     spawned
    0.06
    Act Density 0.007%

    No Known Activations