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

    Neuronpedia

    INDEX
    Explanations

    planning, analysis, and management tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ennemis
    0.44
     malice
    0.42
     salva
    0.40
     mancanza
    0.40
     malu
    0.39
     afect
    0.39
     inflam
    0.39
     aliments
    0.39
     aumentare
    0.38
     signos
    0.38
    POSITIVE LOGITS
     analysis
    0.45
     preparation
    0.42
    preparing
    0.38
    analysis
    0.38
    aining
    0.37
     evaluation
    0.37
     evaluations
    0.37
     assessment
    0.36
     selection
    0.36
    ırmaya
    0.36
    Act Density 0.047%

    No Known Activations