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

    Neuronpedia

    INDEX
    Explanations

    funding and grants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dishonest
    0.77
     használ
    0.74
     melancholy
    0.73
     haunting
    0.71
     always
    0.70
     discoloration
    0.70
     dishonesty
    0.70
     unreliable
    0.68
     sadness
    0.68
     adultery
    0.67
    POSITIVE LOGITS
     funding
    1.65
     funded
    1.65
     Funded
    1.53
     Funding
    1.52
    funded
    1.49
    Funding
    1.41
    funding
    1.32
     financement
    1.31
     финанси
    1.31
     funders
    1.26
    Act Density 0.003%

    No Known Activations