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

    Neuronpedia

    INDEX
    Explanations

    ode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    occo
    -0.07
    zent
    -0.06
    lest
    -0.06
    strstr
    -0.06
    ーラ
    -0.06
    _saved
    -0.06
    olic
    -0.06
    जह
    -0.06
    aptive
    -0.06
    	resp
    -0.06
    POSITIVE LOGITS
     απο
    0.07
    แรง
    0.07
     settling
    0.07
    .Down
    0.07
    igInteger
    0.07
     Execute
    0.07
    완료
    0.07
     accompagn
    0.07
     creating
    0.07
     bombs
    0.07
    Act Density 0.004%

    No Known Activations