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

    Neuronpedia

    INDEX
    Explanations

    character names thorne, vance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hydrochloride
    0.58
    Instruction
    0.54
    Convolution
    0.54
    concat
    0.52
    Javadoc
    0.52
    Implemented
    0.52
    Generated
    0.51
    Hace
    0.51
    Cách
    0.50
     yüzden
    0.50
    POSITIVE LOGITS
    thorpe
    0.68
     believes
    0.66
     authorities
    0.65
     fosters
    0.63
    igan
    0.62
    ian
    0.62
    leigh
    0.62
     planters
    0.61
    ville
    0.61
     understands
    0.61
    Act Density 0.026%

    No Known Activations