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

    Neuronpedia

    INDEX
    Explanations

    select click

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PHASE
    -0.07
    缘
    -0.07
    蜘蛛
    -0.06
    rical
    -0.06
     :.:
    -0.06
    .spatial
    -0.06
    /filter
    -0.06
     Lime
    -0.06
    шка
    -0.06
    ету
    -0.06
    POSITIVE LOGITS
    !");
↵
    0.06
    ..."↵↵
    0.06
    -question
    0.06
    	assertThat
    0.06
     �
    0.06
     ms
    0.06
     episode
    0.06
    DON
    0.06
     som
    0.06
    reducers
    0.06
    Act Density 0.036%

    No Known Activations