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

    Neuronpedia

    INDEX
    Explanations

    small size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    space
    -0.07
    第四
    -0.06
    ут
    -0.06
    convert
    -0.06
    velocity
    -0.06
    inton
    -0.06
    OPS
    -0.06
    getSingleton
    -0.06
    OTP
    -0.06
    getBlock
    -0.05
    POSITIVE LOGITS
    =path
    0.07
     legally
    0.07
     chooser
    0.07
     Binding
    0.07
     Bind
    0.07
     confined
    0.07
     distress
    0.07
     uma
    0.06
     furnishings
    0.06
     forb
    0.06
    Act Density 0.040%

    No Known Activations