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

    Neuronpedia

    INDEX
    Explanations

    . or code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Durchmesser
    0.38
     Oliva
    0.38
     DIRECTION
    0.38
    ClInclude
    0.38
    óst
    0.37
     Sunshine
    0.37
     mínimo
    0.37
     Direction
    0.36
     Reaction
    0.36
    ัศ
    0.36
    POSITIVE LOGITS
    cand
    0.37
     We
    0.36
    িগ
    0.35
    Griff
    0.34
    資
    0.34
    ATP
    0.34
     puddle
    0.34
     Scrib
    0.33
     protested
    0.33
     относятся
    0.33
    Act Density 0.001%

    No Known Activations