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

    Neuronpedia

    INDEX
    Explanations

    embedded components and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reporting
    0.41
     თ
    0.40
     φο
    0.38
     résoudre
    0.38
     underwriting
    0.37
     rán
    0.36
     aware
    0.35
     tov
    0.35
     underval
    0.35
    ότη
    0.35
    POSITIVE LOGITS
     módulos
    0.48
     chambers
    0.42
     embedded
    0.42
     modules
    0.41
    Modules
    0.41
    installation
    0.41
     Install
    0.41
    panels
    0.40
     hollow
    0.39
    getInstalled
    0.39
    Act Density 0.091%

    No Known Activations