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

    Neuronpedia

    INDEX
    Explanations

    journey and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    df
    0.38
    bypass
    0.36
    ^(
    0.36
     Bypass
    0.35
    Moving
    0.34
    ou
    0.34
    transmitted
    0.34
    Ste
    0.33
    def
    0.33
    displaystyle
    0.33
    POSITIVE LOGITS
     into
    0.71
     домой
    0.70
     toward
    0.65
     hacia
    0.63
     towards
    0.63
     undertaken
    0.58
     INTO
    0.57
     menuju
    0.55
     туда
    0.55
     across
    0.54
    Act Density 0.028%

    No Known Activations