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

    Neuronpedia

    INDEX
    Explanations

    voice descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Outstanding
    0.47
    パラ
    0.45
    spar
    0.43
    Successfully
    0.40
    Authorized
    0.40
    Embedded
    0.40
    Parallel
    0.39
     fanc
    0.39
    andin
    0.38
    Sampling
    0.38
    POSITIVE LOGITS
    เร
    0.45
     Reconstruction
    0.42
     "/")
    0.42
     při
    0.41
    연
    0.40
     tegas
    0.39
     Respir
    0.38
     defiant
    0.38
     rejoined
    0.38
     TEMPERATURE
    0.38
    Act Density 0.002%

    No Known Activations