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

    Neuronpedia

    INDEX
    Explanations

    feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sanchez
    -0.07
     mong
    -0.07
    00
    -0.07
     Nokia
    -0.07
     valide
    -0.06
     snag
    -0.06
    06
    -0.06
    rowsing
    -0.06
     hamburg
    -0.06
    Route
    -0.06
    POSITIVE LOGITS
     feelings
    0.16
    感情
    0.07
     feeling
    0.07
    (F
    0.07
     eff
    0.07
    shine
    0.07
    orgen
    0.07
    ings
    0.07
    яття
    0.07
     finer
    0.07
    Act Density 0.011%

    No Known Activations