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

    Neuronpedia

    INDEX
    Explanations

    availability of forms/applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cd
    -0.07
    getPath
    -0.06
    @
    -0.06
     Pakistani
    -0.06
    _override
    -0.06
     UNIQUE
    -0.06
    Titan
    -0.06
    .water
    -0.06
     Atmos
    -0.06
     Institutional
    -0.06
    POSITIVE LOGITS
    197
    0.07
    157
    0.07
     misrepresented
    0.07
    ValueGenerationStrategy
    0.07
    -analysis
    0.07
     motivational
    0.07
     पस
    0.07
     useHistory
    0.06
    anda
    0.06
    fires
    0.06
    Act Density 0.011%

    No Known Activations