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

    Neuronpedia

    INDEX
    Explanations

    small caps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Đo
    -0.07
     Bett
    -0.06
     headphone
    -0.06
    xAD
    -0.06
     takový
    -0.06
    ottie
    -0.06
     öğret
    -0.06
    ometr
    -0.06
    beiter
    -0.06
     싶
    -0.06
    POSITIVE LOGITS
    ervatives
    0.07
     Prime
    0.07
    >Create
    0.06
    (array
    0.06
     suck
    0.06
     small
    0.06
    .ant
    0.06
     Primary
    0.06
    	create
    0.06
     serve
    0.06
    Act Density 0.001%

    No Known Activations