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

    Neuronpedia

    INDEX
    Explanations

    phrasal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     جيد
    0.88
     مسیر
    0.87
     مە
    0.76
    <unused470>
    0.75
     जानना
    0.74
    sym
    0.73
    ခြ
    0.72
    رځ
    0.70
    拠点
    0.70
     ባ
    0.70
    POSITIVE LOGITS
     out
    2.51
     up
    2.14
     forth
    2.08
     away
    2.02
     down
    1.91
     off
    1.72
    out
    1.63
     Away
    1.35
    up
    1.33
     back
    1.32
    Act Density 0.471%

    No Known Activations