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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    스크
    0.26
    물
    0.26
    OPA
    0.25
    스
    0.25
    냐
    0.24
     നൽക
    0.24
    Altura
    0.24
    REN
    0.24
    жка
    0.24
    를
    0.24
    POSITIVE LOGITS
     }
    0.22
     Cemetery
    0.22
     characterised
    0.22
    ttl
    0.22
     /*
    0.21
        
    0.21
     insured
    0.21
     Beach
    0.21
     smiles
    0.20
     attributable
    0.20
    Act Density 0.021%

    No Known Activations