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

    Neuronpedia

    INDEX
    Explanations

    J' followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রদত্ত
    0.86
    setContentType
    0.82
     வள
    0.82
    кси
    0.79
     persoane
    0.77
     jabatan
    0.76
     dressing
    0.76
     longitud
    0.75
     KMnO
    0.73
     リュック
    0.73
    POSITIVE LOGITS
     magnificent
    0.76
     ε
    0.74
    gesch
    0.67
     shilling
    0.67
    მოს
    0.66
     enfe
    0.66
     glorious
    0.65
     sublime
    0.63
    рил
    0.63
     gorgeous
    0.63
    Act Density 0.005%

    No Known Activations