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

    Neuronpedia

    INDEX
    Explanations

    disputes, claims, costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वासीय
    0.40
     παρα
    0.39
    issam
    0.39
     স্থ
    0.38
    owanej
    0.38
    输
    0.38
    猟
    0.38
    ंति
    0.38
    ρκ
    0.38
     corta
    0.38
    POSITIVE LOGITS
     claim
    0.70
     claims
    0.70
     Claims
    0.68
    claims
    0.68
    Claim
    0.65
    Claims
    0.63
     claiming
    0.62
     Claim
    0.62
    claim
    0.59
    CLAIM
    0.57
    Act Density 0.025%

    No Known Activations