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

    Neuronpedia

    INDEX
    Explanations

    allegedly/reportedly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CY
    -0.07
     tunnels
    -0.06
     signIn
    -0.06
    ологіч
    -0.06
     cycles
    -0.06
     Priest
    -0.06
     cryptoc
    -0.06
    psi
    -0.06
     Sea
    -0.06
     windowHeight
    -0.06
    POSITIVE LOGITS
     allegedly
    0.12
     reportedly
    0.12
     apparently
    0.08
     presumably
    0.07
     ostensibly
    0.07
    .registry
    0.07
    ?????
    0.07
    Apparently
    0.07
    _IMPORTED
    0.07
    rame
    0.07
    Act Density 0.009%

    No Known Activations