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

    Neuronpedia

    INDEX
    Explanations

    allies or ally with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    з
    1.91
     bunting
    1.88
     rectal
    1.77
    }$}
    1.69
     tillage
    1.68
     tinnitus
    1.67
     cardiology
    1.66
     dialysis
    1.64
     nutshell
    1.63
     abstinence
    1.61
    POSITIVE LOGITS
    ä
    2.25
    uft
    2.08
    g
    2.02
    اً
    1.98
    от
    1.95
    uat
    1.94
    brigen
    1.94
    erdings
    1.93
    ut
    1.91
    arı
    1.88
    Act Density 0.002%

    No Known Activations