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

    Neuronpedia

    INDEX
    Explanations

    making a claim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eliminate
    0.47
     Dread
    0.43
    篑
    0.42
     KAHN
    0.42
     किसको
    0.42
     FLOR
    0.41
     MOH
    0.41
     REIT
    0.41
     MUSE
    0.40
    '])){
    0.40
    POSITIVE LOGITS
     claims
    0.68
     claim
    0.67
     Claim
    0.66
     claimed
    0.66
    claims
    0.64
    claim
    0.60
     claiming
    0.59
    Claim
    0.59
    claimer
    0.58
    claiming
    0.58
    Act Density 0.006%

    No Known Activations