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

    Neuronpedia

    INDEX
    Explanations

    dangerous situations/rescue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fiction
    -0.08
    ={({
    -0.07
    ḻ
    -0.07
    פל
    -0.07
    垞
    -0.07
    .VALUE
    -0.07
    _pagination
    -0.07
    (chalk
    -0.07
     concessions
    -0.07
    _business
    -0.06
    POSITIVE LOGITS
     extreme
    0.07
    	State
    0.07
     linha
    0.07
     Modify
    0.07
     imprisoned
    0.07
    �
    0.07
    getDate
    0.07
     이미
    0.06
     diss
    0.06
     anál
    0.06
    Act Density 0.080%

    No Known Activations