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

    Neuronpedia

    INDEX
    Explanations

    LLM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forbids
    0.41
     liberté
    0.37
     humanos
    0.35
     cramps
    0.35
     umani
    0.34
     naranja
    0.34
     warns
    0.33
     humains
    0.33
     laranja
    0.33
     raspberries
    0.33
    POSITIVE LOGITS
    Election
    0.35
    cedures
    0.34
    mathcal
    0.32
    த்தின்
    0.32
     Moving
    0.31
    🔎
    0.31
     экземпля
    0.30
    峒
    0.30
    ixon
    0.30
     Artifact
    0.30
    Act Density 0.103%

    No Known Activations