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

    Neuronpedia

    INDEX
    Explanations

    model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    फना
    0.63
     کھل
    0.63
     परी
    0.59
     Marne
    0.59
    access
    0.59
     drainage
    0.59
    កំណ
    0.56
    ணற
    0.56
    ENTRY
    0.55
    Access
    0.55
    POSITIVE LOGITS
     OK
    0.56
     القط
    0.53
    ക്കാ
    0.53
    deut
    0.53
    NOS
    0.52
     Duct
    0.51
     double
    0.50
     single
    0.50
     Double
    0.49
     Single
    0.49
    Act Density 0.216%

    No Known Activations