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

    Neuronpedia

    INDEX
    Explanations

    more technical or very hot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ième
    0.55
     gotas
    0.55
     venezolano
    0.54
    śmy
    0.53
     cantidades
    0.53
    way
    0.52
     posiblemente
    0.52
    s
    0.51
     tanque
    0.51
    on
    0.50
    POSITIVE LOGITS
    0.57
    0.54
    0.53
    U
    0.52
    0.51
     Thus
    0.48
    語
    0.48
    어
    0.47
     Ravens
    0.46
     stagnant
    0.46
    Act Density 0.904%

    No Known Activations