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

    Neuronpedia

    INDEX
    Explanations

    weather prediction models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ankles
    0.69
     astring
    0.63
     attacking
    0.61
     ASTM
    0.59
     PTFE
    0.58
     FTSE
    0.57
     morale
    0.57
     undue
    0.56
     doxycycline
    0.56
     torsional
    0.56
    POSITIVE LOGITS
    expires
    0.63
    ෙන්ම
    0.61
    ش
    0.59
    führt
    0.55
    бира
    0.54
    faat
    0.54
    эд
    0.54
    -}
    0.54
    </h5>
    0.53
    ли
    0.53
    Act Density 0.002%

    No Known Activations