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

    Neuronpedia

    INDEX
    Explanations

    resist, reluctantly, and counterintuitive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    בה
    0.41
     dechlor
    0.40
     across
    0.39
    釹
    0.39
    ων
    0.39
     SNMP
    0.39
     casually
    0.37
     browsers
    0.37
    বসাইটে
    0.37
     assessing
    0.37
    POSITIVE LOGITS
     resist
    0.69
     resisting
    0.64
     resistência
    0.64
     сопротив
    0.64
     resistenza
    0.63
     reluctance
    0.63
     reluctantly
    0.60
     resists
    0.59
     reluctant
    0.59
     resistencia
    0.59
    Act Density 0.074%

    No Known Activations