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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scenario
    -0.07
    над
    -0.07
    ccak
    -0.07
     Utf
    -0.07
     Empire
    -0.07
    ้ร
    -0.07
    mach
    -0.07
    teste
    -0.06
    .Areas
    -0.06
     involuntary
    -0.06
    POSITIVE LOGITS
     herhangi
    0.06
    ABILITY
    0.06
     fanc
    0.06
     pellets
    0.06
     leave
    0.06
     И
    0.06
     compagn
    0.05
    erness
    0.05
     invokingState
    0.05
    ING
    0.05
    Act Density 0.000%

    No Known Activations