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

    Neuronpedia

    INDEX
    Explanations

    und

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erd
    0.96
    erst
    0.94
    erde
    0.94
    andrew
    0.92
    erg
    0.90
    erns
    0.88
    eric
    0.86
    heni
    0.86
    oció
    0.85
    uegos
    0.85
    POSITIVE LOGITS
     treating
    0.79
     putting
    0.77
     inhibiting
    0.70
     shutting
    0.70
     browse
    0.67
     reassuring
    0.66
     placing
    0.65
     neutralize
    0.65
     looking
    0.65
     suppressing
    0.64
    Act Density 0.000%

    No Known Activations