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

    Neuronpedia

    INDEX
    Explanations

    say equals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blah
    -0.07
     lucky
    -0.07
    因此
    -0.06
    .”↵↵↵↵
    -0.06
    由此
    -0.06
    �
    -0.06
     secondo
    -0.06
    pictured
    -0.06
    _login
    -0.06
     piles
    -0.06
    POSITIVE LOGITS
    requested
    0.07
     looking
    0.07
    Tracking
    0.07
     suggest
    0.07
    _Request
    0.07
    航班
    0.07
    	request
    0.07
    document
    0.07
     interrogation
    0.07
    𝘔
    0.07
    Act Density 0.007%

    No Known Activations