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

    Neuronpedia

    INDEX
    Explanations

    adds to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permita
    0.72
     ability
    0.71
     evitando
    0.69
     templates
    0.65
     evitar
    0.65
     instilled
    0.63
     blueprint
    0.62
     permits
    0.62
     ignoring
    0.62
     rediscover
    0.62
    POSITIVE LOGITS
     adds
    1.53
     Adds
    1.47
     add
    1.44
    Adds
    1.38
     adding
    1.36
     Add
    1.34
    Add
    1.33
     added
    1.33
     допъл
    1.32
     additions
    1.31
    Act Density 0.553%

    No Known Activations