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

    Neuronpedia

    INDEX
    Explanations

    evidence and observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     identities
    0.48
     Depending
    0.48
    Exact
    0.47
     depending
    0.44
    Depending
    0.43
     exact
    0.42
     acquired
    0.41
    exact
    0.40
     identity
    0.39
     potentially
    0.39
    POSITIVE LOGITS
     evidenced
    0.76
     observar
    0.75
     दिसून
    0.68
     observable
    0.67
     Indications
    0.66
     Evidence
    0.64
     evidence
    0.64
     видно
    0.63
     visibly
    0.62
     observed
    0.61
    Act Density 0.118%

    No Known Activations