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

    Neuronpedia

    INDEX
    Explanations

    attempting to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    argmax
    0.50
    HttpPut
    0.49
    ախ
    0.46
    न्ट
    0.46
     फरार
    0.45
    alarını
    0.45
    σετε
    0.45
    dependencies
    0.44
     অর
    0.44
    vanje
    0.44
    POSITIVE LOGITS
     seasonal
    0.49
     moisture
    0.48
     any
    0.47
     personnels
    0.46
     anything
    0.46
     Merle
    0.45
     way
    0.44
     anyone
    0.44
     solos
    0.44
     technique
    0.44
    Act Density 0.015%

    No Known Activations