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

    Neuronpedia

    INDEX
    Explanations

    approve or inform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    give
    0.40
    Highly
    0.38
    GU
    0.37
    Scaled
    0.37
    ympathetic
    0.36
    vit
    0.36
    </sup>
    0.36
    highly
    0.36
     vitam
    0.35
     Highly
    0.34
    POSITIVE LOGITS
     aprobar
    0.59
     approves
    0.53
     approve
    0.52
     approved
    0.50
     Inform
    0.49
    批准
    0.47
     informer
    0.47
    approve
    0.46
    Inform
    0.46
    APPROVAL
    0.46
    Act Density 0.000%

    No Known Activations