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

    Neuronpedia

    INDEX
    Explanations

    exceptions or contrasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folder
    -0.07
    .Hand
    -0.07
    ศ
    -0.07
    olutely
    -0.07
     relaxing
    -0.07
    _bw
    -0.07
    资金
    -0.06
    osome
    -0.06
    -C
    -0.06
     suddenly
    -0.06
    POSITIVE LOGITS
    strconv
    0.08
     except
    0.06
    .ejb
    0.06
     Tenn
    0.06
     blender
    0.06
    Leap
    0.06
    /entities
    0.06
     топ
    0.06
    onga
    0.05
    mekte
    0.05
    Act Density 0.016%

    No Known Activations