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

    Neuronpedia

    INDEX
    Explanations

    I followed by 'll

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vliegt
    0.39
     ganglion
    0.38
     volt
    0.38
     enorm
    0.38
     wides
    0.38
    ذن
    0.38
     eosin
    0.38
     splashes
    0.37
     splen
    0.37
     metastases
    0.37
    POSITIVE LOGITS
     It
    0.49
    厳しい
    0.45
    ata
    0.45
    oc
    0.45
     Despite
    0.45
    ami
    0.44
    iremos
    0.44
    Despite
    0.43
    ựa
    0.43
    asked
    0.43
    Act Density 0.097%

    No Known Activations