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

    Neuronpedia

    INDEX
    Explanations

    want to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Being
    0.29
    they
    0.29
     Becoming
    0.27
     kwamba
    0.26
    being
    0.26
     необходимые
    0.25
    odesmium
    0.25
    ibers
    0.24
    梁
    0.24
    required
    0.24
    POSITIVE LOGITS
     us
    0.50
     them
    0.48
     assurances
    0.48
     me
    0.48
     assurance
    0.47
     want
    0.46
     assistance
    0.45
     rid
    0.44
     reassurance
    0.44
     him
    0.43
    Act Density 0.151%

    No Known Activations