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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ilişkin
    -0.07
    chk
    -0.06
    Global
    -0.06
     دید
    -0.06
     сем
    -0.06
    ,the
    -0.06
    bole
    -0.06
     virt
    -0.06
    many
    -0.06
    itest
    -0.06
    POSITIVE LOGITS
    _LR
    0.07
    
    0.07
     Phillies
    0.06
     Isabel
    0.06
    -water
    0.06
     tapered
    0.06
    bab
    0.06
    вай
    0.06
     explodes
    0.06
     Published
    0.06
    Act Density 0.003%

    No Known Activations