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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    هوری
    -0.07
    .strict
    -0.07
    emony
    -0.07
    ович
    -0.06
    cx
    -0.06
    ança
    -0.06
    _keep
    -0.06
    	stat
    -0.06
     twee
    -0.06
    ова
    -0.06
    POSITIVE LOGITS
    แกรม
    0.07
    Spring
    0.07
     rubbed
    0.06
     Yas
    0.06
    يل
    0.06
     ال
    0.06
    During
    0.06
    Mu
    0.06
    oupon
    0.06
     a
    0.06
    Act Density 0.035%

    No Known Activations