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

    Neuronpedia

    INDEX
    Explanations

    handle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     backwards
    -0.07
     اختل
    -0.07
     regression
    -0.06
    <message
    -0.06
    maj
    -0.06
    rypted
    -0.06
     Cursor
    -0.06
     rejection
    -0.06
    redient
    -0.06
     Medicare
    -0.06
    POSITIVE LOGITS
    Manual
    0.07
    ¯Â
    0.07
     forKey
    0.06
    首页
    0.06
    [%
    0.06
    	ch
    0.06
    escort
    0.06
     shut
    0.06
     رفته
    0.06
    ev
    0.06
    Act Density 0.000%

    No Known Activations