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

    Neuronpedia

    INDEX
    Explanations

    continue fightingstress responseenabling featurescousin scenariossending messagesrainy day activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Liquid
    0.41
     ছেলেদের
    0.39
    every
    0.39
    Getting
    0.38
    Hybrid
    0.38
    Flux
    0.38
    GeneratedValue
    0.38
    発展
    0.37
    Inst
    0.37
    Individuals
    0.37
    POSITIVE LOGITS
     Dian
    0.44
     bent
    0.42
     Ort
    0.42
     Zor
    0.41
    lepas
    0.41
     hil
    0.41
     bund
    0.40
     metu
    0.40
     wrapping
    0.39
     turquoise
    0.39
    Act Density 0.000%

    No Known Activations