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

    Neuronpedia

    INDEX
    Explanations

    spit out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.37
    land
    0.36
    self
    0.35
     l
    0.35
    est
    0.33
     una
    0.33
    upy
    0.32
    served
    0.31
    I
    0.31
    end
    0.30
    POSITIVE LOGITS
     diş
    0.47
     Mouth
    0.43
    牙
    0.43
    🦷
    0.42
     buccal
    0.40
     दांत
    0.40
     jaw
    0.40
     Verfü
    0.39
     Dental
    0.38
    𝗍
    0.38
    Act Density 0.006%

    No Known Activations