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

    Neuronpedia

    INDEX
    Explanations

    stages and dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     true
    0.44
     filter
    0.39
     succ
    0.39
     tester
    0.39
    让
    0.39
     poss
    0.38
     tape
    0.38
     test
    0.37
     thr
    0.37
     sar
    0.37
    POSITIVE LOGITS
     exogenous
    0.43
     abandonar
    0.42
    Schwe
    0.42
    olinha
    0.40
     estuvieron
    0.40
     पर्यावरणीय
    0.40
    年度
    0.39
     француз
    0.39
    environmental
    0.38
     grandiose
    0.38
    Act Density 0.001%

    No Known Activations