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

    Neuronpedia

    INDEX
    Explanations

    plays on pronunciation, wordplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     U
    0.51
     spite
    0.50
     pirate
    0.47
     state
    0.46
     schist
    0.46
     p
    0.46
     strtok
    0.46
     d
    0.45
     and
    0.45
     reactor
    0.45
    POSITIVE LOGITS
    Psal
    0.55
    avasena
    0.52
    lden
    0.48
     পরিবর্তে
    0.47
    leece
    0.47
    髅
    0.47
    lde
    0.46
    Hun
    0.46
    Altern
    0.46
    ییر
    0.46
    Act Density 0.004%

    No Known Activations