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

    Neuronpedia

    INDEX
    Explanations

    Mental health treatment/hospitalization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	dispatch
    -0.08
     Fragment
    -0.07
    :int
    -0.07
     slender
    -0.07
    だから
    -0.07
    〘
    -0.07
     scenes
    -0.07
    [tag
    -0.07
     chociaż
    -0.07
     одного
    -0.06
    POSITIVE LOGITS
    kea
    0.07
    erah
    0.07
    يص
    0.07
    akış
    0.07
     amacı
    0.07
    ቦ
    0.06
    纥
    0.06
    ladı
    0.06
    eo
    0.06
    anye
    0.06
    Act Density 0.036%

    No Known Activations