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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tren
    -0.07
     injection
    -0.07
     landmark
    -0.07
     Invasion
    -0.06
    -energy
    -0.06
    requestCode
    -0.06
    	full
    -0.06
    по
    -0.06
    งของ
    -0.06
    Ob
    -0.06
    POSITIVE LOGITS
    .dst
    0.07
     Ange
    0.07
    purple
    0.07
     dst
    0.07
    _sk
    0.06
    _SEQUENCE
    0.06
     Jane
    0.06
    .stack
    0.06
     warnings
    0.06
     taxed
    0.06
    Act Density 0.002%

    No Known Activations