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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æıIJ示
    -0.30
    rats
    -0.28
    ä¿¡åı·
    -0.27
    è´´
    -0.26
    Tube
    -0.25
    éĢļ
    -0.25
    éĹ®é¢ĺ
    -0.25
     signal
    -0.25
     Polymer
    -0.25
    Stencil
    -0.25
    POSITIVE LOGITS
    éĽģ
    0.24
    çıŃåŃIJæĪIJåijĺ
    0.24
    ÑĨип
    0.24
    ä¹¾
    0.24
     Lives
    0.24
     опÑĭ
    0.24
     analysed
    0.23
     dunk
    0.23
     experiment
    0.23
    (fr
    0.23
    Act Density 0.728%

    No Known Activations