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

    Neuronpedia

    INDEX
    Explanations

    idiomatic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trop
    0.38
    RT
    0.38
    Preprocessor
    0.38
    éria
    0.38
    beige
    0.38
    calorie
    0.37
     મહે
    0.37
     ND
    0.36
    Retro
    0.36
    oyo
    0.36
    POSITIVE LOGITS
     idiom
    0.96
    omatic
    0.89
     idioms
    0.89
     idi
    0.89
     Idi
    0.88
    Idi
    0.78
    мати
    0.74
    matic
    0.65
     idiopathic
    0.59
    idi
    0.57
    Act Density 0.002%

    No Known Activations