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

    Neuronpedia

    INDEX
    Explanations

    developed and released

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smirk
    0.85
     muttered
    0.84
    ichever
    0.81
     sullen
    0.81
     oppressive
    0.78
     disdain
    0.77
     commas
    0.77
     devoid
    0.76
     superstitious
    0.76
     mumbled
    0.76
    POSITIVE LOGITS
     funded
    1.85
     spearheaded
    1.70
     Funded
    1.65
     initiative
    1.62
    funded
    1.59
     launched
    1.58
     Launched
    1.57
     jointly
    1.55
    initiative
    1.51
     aims
    1.49
    Act Density 0.456%

    No Known Activations