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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -component
    -0.07
     Baths
    -0.06
    �
    -0.06
     expl
    -0.06
    mgr
    -0.06
     работа
    -0.06
    $str
    -0.06
     सज
    -0.06
     
    -0.06
    ussed
    -0.06
    POSITIVE LOGITS
     losing
    0.07
     &↵
    0.07
    Labels
    0.07
     Hawaii
    0.07
    şam
    0.07
    لاة
    0.06
    	RuntimeObject
    0.06
     Phen
    0.06
    (Calendar
    0.06
     hitting
    0.06
    Act Density 0.000%

    No Known Activations