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

    Neuronpedia

    INDEX
    Explanations

    host/integrations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     przec
    0.66
     fleur
    0.66
     MTLTexture
    0.62
     Nantes
    0.61
     FeCl
    0.61
     बढ़ाने
    0.60
     Mahabhar
    0.60
     distX
    0.60
     Betracht
    0.59
     tué
    0.58
    POSITIVE LOGITS
    Hosts
    0.62
    agement
    0.59
    HOST
    0.58
     validations
    0.57
    Quick
    0.55
    ITE
    0.55
    воро
    0.54
     connections
    0.53
    Policies
    0.53
    Validation
    0.52
    Act Density 0.001%

    No Known Activations