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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    安心
    -0.07
    COM
    -0.07
     Geography
    -0.07
     CV
    -0.07
    북
    -0.07
    的目标
    -0.07
    我的
    -0.07
    .Email
    -0.07
     suggestions
    -0.07
     spl
    -0.07
    POSITIVE LOGITS
     shipments
    0.07
    0.07
    ﺙ
    0.06
     dropping
    0.06
    (vm
    0.06
    	pc
    0.06
     drinkers
    0.06
    _flat
    0.06
    	damage
    0.06
    🚬
    0.06
    Act Density 0.001%

    No Known Activations