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

    Neuronpedia

    INDEX
    Explanations

    thus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erna
    -0.07
    /ne
    -0.06
     Kerry
    -0.06
    Bei
    -0.06
     deter
    -0.06
     scrambled
    -0.06
    obre
    -0.06
    �
    -0.06
    μενη
    -0.06
    reiben
    -0.06
    POSITIVE LOGITS
     thus
    0.13
     Thus
    0.09
    Thus
    0.08
    (as
    0.07
     Results
    0.07
    _AST
    0.07
     Toxic
    0.07
    ASH
    0.07
    (conn
    0.07
    UNIX
    0.07
    Act Density 0.012%

    No Known Activations