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

    Neuronpedia

    INDEX
    Explanations

    AM PM time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ั่ว
    0.47
     رہنے
    0.41
    ើយ
    0.40
     ورځې
    0.39
    Uuid
    0.38
    Directive
    0.38
    ۴
    0.38
     દિવસે
    0.38
     হেতু
    0.38
    %%%%%%%%%%%%
    0.37
    POSITIVE LOGITS
    pm
    1.13
     pm
    1.04
     PM
    0.97
    PM
    0.85
    am
    0.74
     बजे
    0.70
    पीएम
    0.62
     am
    0.61
     AM
    0.55
     pam
    0.55
    Act Density 0.011%

    No Known Activations