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

    Neuronpedia

    INDEX
    Explanations

    specific domain terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ви
    0.49
     mejorar
    0.47
     FR
    0.45
     melhorar
    0.45
     ο
    0.44
     अगली
    0.44
    oplas
    0.44
     multiplicar
    0.44
     APC
    0.43
     UFC
    0.43
    POSITIVE LOGITS
    LinkedIn
    0.50
     holds
    0.47
    oursquare
    0.47
    ยน
    0.45
    Twitter
    0.44
    сера
    0.43
    stories
    0.43
    6
    0.43
    mck
    0.42
     swat
    0.42
    Act Density 0.001%

    No Known Activations