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

    Neuronpedia

    INDEX
    Explanations

    contraction for 'is' or 'was'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ',
    0.42
    怆
    0.39
    ldef
    0.39
    uka
    0.38
    "',
    0.38
    axon
    0.38
    ênd
    0.37
     lleve
    0.37
    屹
    0.37
    \
    0.37
    POSITIVE LOGITS
     asleep
    0.63
     complaining
    0.59
     jealous
    0.57
     snoring
    0.56
     impatient
    0.55
     homophobic
    0.54
     unwell
    0.52
     allergic
    0.51
     schizophren
    0.51
     rumoured
    0.51
    Act Density 0.008%

    No Known Activations