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

    Neuronpedia

    INDEX
    Explanations

    forklift and its operation or accidents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.70
    mates
    0.57
    {\
    0.50
    е
    0.49
    ுங்கள்
    0.49
    erol
    0.48
    erà
    0.47
    う
    0.46
    ी
    0.45
    erg
    0.45
    POSITIVE LOGITS
     Bein
    0.61
    ます
    0.56
    稞
    0.55
     ৮০
    0.55
    ภัย
    0.55
     najve
    0.55
     niektó
    0.54
    Maar
    0.54
     nahezu
    0.54
     mulig
    0.53
    Act Density 0.002%

    No Known Activations