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

    Neuronpedia

    INDEX
    Explanations

    anxieties and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     admire
    0.51
     despise
    0.48
    芸能
    0.48
    кономі
    0.47
    ใด
    0.47
     politely
    0.47
     inciting
    0.47
    0.46
     aromat
    0.45
     efeitos
    0.45
    POSITIVE LOGITS
    ale
    0.42
    كامل
    0.42
    klam
    0.41
    ädig
    0.40
    㓡
    0.40
    il
    0.40
     Gardiner
    0.39
    u
    0.39
     Forestry
    0.39
     Goals
    0.38
    Act Density 0.003%

    No Known Activations