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

    Neuronpedia

    INDEX
    Explanations

    Fenton, Eddi, Майк

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.27
     roughly
    0.27
    as
    0.25
     vastly
    0.25
    ation
    0.24
     VERY
    0.24
     rhymes
    0.24
    िकर
    0.24
    able
    0.24
     ICO
    0.24
    POSITIVE LOGITS
     repente
    0.27
     ilegal
    0.27
    )}_
    0.26
     pediu
    0.25
    ិត្ត
    0.25
     estrada
    0.24
     deewana
    0.24
    venido
    0.24
    ashington
    0.24
     delitos
    0.24
    Act Density 0.021%

    No Known Activations