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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    keep
    -0.07
     alliances
    -0.06
    VersionUID
    -0.06
    ív
    -0.06
    .BindingSource
    -0.06
    [it
    -0.06
     ksi
    -0.06
    subst
    -0.06
    �
    -0.06
    руб
    -0.06
    POSITIVE LOGITS
     dipping
    0.07
    Further
    0.06
     내
    0.06
     перен
    0.06
     kapsamında
    0.06
     mé
    0.06
     alanında
    0.06
     ilişkin
    0.06
     liệt
    0.06
    udded
    0.06
    Act Density 0.003%

    No Known Activations