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

    Neuronpedia

    INDEX
    Explanations

    spree, decree, plea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acidade
    0.46
    으로
    0.44
     으로
    0.44
    वारा
    0.44
    ndt
    0.43
    이라는
    0.43
    transitions
    0.43
    tenance
    0.42
     although
    0.41
    transformed
    0.41
    POSITIVE LOGITS
    zy
    0.58
    zle
    0.48
    ء
    0.46
    indruck
    0.44
    зы
    0.43
    eee
    0.42
     szükség
    0.41
     sockets
    0.41
    zew
    0.39
    х
    0.39
    Act Density 0.025%

    No Known Activations