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

    Neuronpedia

    INDEX
    Explanations

    prototype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Address
    -0.07
    Areas
    -0.07
     ecosystem
    -0.06
     chic
    -0.06
     Services
    -0.06
     fear
    -0.06
    839
    -0.06
     INFORMATION
    -0.06
    Sex
    -0.06
     hitting
    -0.06
    POSITIVE LOGITS
     prototypes
    0.11
     prototype
    0.11
     prot
    0.09
     Prototype
    0.08
    Prototype
    0.08
     Prot
    0.08
    .PRO
    0.08
    proto
    0.08
    û
    0.08
     onChange
    0.07
    Act Density 0.008%

    No Known Activations