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

    Neuronpedia

    INDEX
    Explanations

    staring at, into, out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sonya
    0.45
     precipitation
    0.43
    شاعرانه
    0.42
    REFERENCE
    0.41
    來看
    0.41
    サスカ
    0.39
     puncture
    0.39
     ornamentation
    0.38
     হেসে
    0.38
    संदर्भ
    0.38
    POSITIVE LOGITS
    ાળ
    0.40
    At
    0.39
    Md
    0.38
    undefined
    0.38
    Pl
    0.38
    emb
    0.37
    Под
    0.37
    erenza
    0.37
    挂
    0.36
     emb
    0.36
    Act Density 0.000%

    No Known Activations