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

    Neuronpedia

    INDEX
    Explanations

    relative to point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decided
    0.42
     stipulated
    0.42
     definite
    0.40
     Equation
    0.40
     metallic
    0.40
    VIOUS
    0.39
     confessed
    0.39
     hearts
    0.38
     angel
    0.38
     angeles
    0.38
    POSITIVE LOGITS
    d
    0.58
     vì
    0.49
    dü
    0.49
    ആര്‍
    0.49
    เวอร์
    0.49
    nętr
    0.48
    닉
    0.47
    ⌛
    0.47
    ä
    0.47
     nå
    0.46
    Act Density 0.000%

    No Known Activations