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

    Neuronpedia

    INDEX
    Explanations

    Software safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .normalize
    -0.07
     RedirectTo
    -0.07
    产业
    -0.07
     mall
    -0.06
     didSelect
    -0.06
    ़ो
    -0.06
    Tes
    -0.06
     Subcommittee
    -0.06
    ště
    -0.06
     στρα
    -0.06
    POSITIVE LOGITS
    IVERS
    0.06
     COUNT
    0.06
    ても
    0.06
     getUser
    0.06
    phil
    0.05
     Aw
    0.05
    CLUDING
    0.05
    	
↵
    0.05
    _DEFIN
    0.05
     volley
    0.05
    Act Density 0.023%

    No Known Activations