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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snapshot
    -0.07
     прож
    -0.07
     PRODUCT
    -0.07
    -arrow
    -0.07
     ده
    -0.06
    TRANSFER
    -0.06
     एस
    -0.06
    yslu
    -0.06
     nonprofit
    -0.06
    -0.06
    POSITIVE LOGITS
    ].'
    0.07
    _DRIVER
    0.07
    ’na
    0.06
    에서는
    0.06
    أة
    0.06
     stunt
    0.06
    .ASCII
    0.06
    .Resource
    0.06
     thang
    0.06
     dmg
    0.06
    Act Density 0.058%

    No Known Activations