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

    Neuronpedia

    INDEX
    Explanations

    vulnerability identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rupani
    0.29
     formules
    0.25
    萜
    0.25
    వ్వు
    0.25
     ennemis
    0.25
    BlockUsed
    0.25
     anodes
    0.25
     mètres
    0.24
     അള
    0.24
     globules
    0.24
    POSITIVE LOGITS
    2
    0.36
    0.34
    9
    0.33
    7
    0.32
    6
    0.31
    8
    0.31
    1
    0.31
    3
    0.30
    4
    0.30
    end
    0.29
    Act Density 0.072%

    No Known Activations