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

    Neuronpedia

    INDEX
    Explanations

    or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mine
    0.51
     Melting
    0.49
     Jumbo
    0.48
    atient
    0.46
    getPackageName
    0.46
    ineri
    0.45
    ריך
    0.45
    മ്പി
    0.44
    Mini
    0.44
    だけに
    0.44
    POSITIVE LOGITS
     atau
    0.89
     oppure
    0.87
     hoặc
    0.86
    あるいは
    0.84
     또는
    0.82
    或者
    0.80
    或其他
    0.80
    或者是
    0.79
     혹은
    0.77
     অথবা
    0.76
    Act Density 0.028%

    No Known Activations