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

    Neuronpedia

    INDEX
    Explanations

    freshly cracked or ground

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pepper
    0.81
     Pepper
    0.80
     pepper
    0.79
    pepper
    0.78
     Peppers
    0.70
    PEP
    0.66
     Pep
    0.66
    Pep
    0.65
     peppers
    0.64
     PEP
    0.62
    POSITIVE LOGITS
     Sarawak
    0.50
     cor
    0.43
     kuy
    0.40
    Tell
    0.39
    㕫
    0.39
     thermocou
    0.39
     cornea
    0.38
     Malaysia
    0.38
     Tell
    0.38
     cracked
    0.38
    Act Density 0.007%

    No Known Activations