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

    Neuronpedia

    INDEX
    Explanations

    implications and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    0.93
    jší
    0.80
    äck
    0.72
     C
    0.68
     I
    0.68
    ävä
    0.68
     '
    0.65
    reeze
    0.65
     fysis
    0.65
    ter
    0.64
    POSITIVE LOGITS
     Implications
    1.05
     implications
    0.95
     consequences
    0.94
    ర్
    0.93
    न
    0.90
     repercussions
    0.89
     последствия
    0.89
     Consequences
    0.88
     conséquences
    0.88
     consecuencia
    0.86
    Act Density 0.259%

    No Known Activations