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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ється
    -0.06
    чаются
    -0.06
    ABCDE
    -0.06
     Persons
    -0.06
     záb
    -0.06
    ีเด
    -0.06
    .repo
    -0.06
    Feb
    -0.06
     lengthy
    -0.06
    ується
    -0.06
    POSITIVE LOGITS
     Components
    0.07
    μερ
    0.07
    -Token
    0.06
    ront
    0.06
    rowing
    0.06
     erect
    0.06
    generated
    0.06
     grotes
    0.06
     Revenge
    0.06
    declare
    0.06
    Act Density 0.000%

    No Known Activations