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

    Neuronpedia

    INDEX
    Explanations

    respect and appreciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ensureEqual
    0.43
    topics
    0.36
    いくつかの
    0.35
    ospel
    0.33
    ក់
    0.33
    Lx
    0.32
     quantités
    0.32
    Make
    0.32
    recated
    0.32
     Extending
    0.32
    POSITIVE LOGITS
     respectful
    0.60
     appreciate
    0.57
     autonomy
    0.54
     appreciates
    0.54
     efforts
    0.54
     individuality
    0.54
     diversity
    0.53
     sovereignty
    0.53
     appreciation
    0.53
     acknowledge
    0.52
    Act Density 0.015%

    No Known Activations