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

    Neuronpedia

    INDEX
    Explanations

    specific philosophy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kerap
    0.49
    ब
    0.46
    <0xA8>
    0.45
    берём
    0.44
    ;\
    0.43
    n
    0.43
     deterior
    0.42
     easing
    0.42
    autical
    0.41
    <0x99>
    0.41
    POSITIVE LOGITS
     Ato
    0.52
     Prometheus
    0.46
    Listo
    0.45
    Prefs
    0.44
    Oi
    0.43
     Inhalte
    0.43
    Golem
    0.43
     Succ
    0.42
     Plugins
    0.42
     Qo
    0.42
    Act Density 0.001%

    No Known Activations