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

    Neuronpedia

    INDEX
    Explanations

    be prompted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     receive
    1.16
     receives
    1.07
     receiving
    1.06
    receiving
    1.04
     Receiving
    1.02
     recieve
    1.01
     reciben
    0.97
     recibe
    0.96
    receive
    0.93
     Receive
    0.92
    POSITIVE LOGITS
    Prom
    0.78
    Promotion
    0.73
     Prom
    0.73
     untenable
    0.72
    ကျ
    0.71
    Pro
    0.70
    Provenance
    0.70
    prom
    0.69
    CONT
    0.69
    Been
    0.68
    Act Density 0.013%

    No Known Activations