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

    Neuronpedia

    INDEX
    Explanations

    Evaluating technical and communication abilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comentários
    0.46
     fortunes
    0.42
     membahas
    0.40
     aventuras
    0.40
    解説
    0.39
     enviados
    0.39
     adventures
    0.39
     discussion
    0.39
    WithOwner
    0.38
     komment
    0.38
    POSITIVE LOGITS
     ability
    0.65
     Ability
    0.64
    Ability
    0.60
     оцени
    0.59
     Evaluating
    0.55
     evaluating
    0.54
     Evaluation
    0.53
    评估
    0.53
     interpreting
    0.52
     assessing
    0.52
    Act Density 0.016%

    No Known Activations