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

    Neuronpedia

    INDEX
    Explanations

    becoming computerized, disputes between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prioritize
    0.48
     पीड़ित
    0.45
     navigate
    0.44
     participate
    0.44
     predict
    0.44
     do
    0.43
     improve
    0.43
     explore
    0.43
     locate
    0.43
     analyze
    0.42
    POSITIVE LOGITS
     Amongst
    0.42
     Scattering
    0.41
    POP
    0.40
    τσι
    0.39
    at
    0.39
    兩
    0.38
    soul
    0.37
    y
    0.37
    sad
    0.36
    hah
    0.36
    Act Density 0.017%

    No Known Activations