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

    Neuronpedia

    INDEX
    Explanations

    air temperature

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hierarchy
    -0.08
    newline
    -0.08
    ierarchy
    -0.07
    -arm
    -0.07
     ey
    -0.07
    roc
    -0.07
    -ROM
    -0.06
     synthesis
    -0.06
     Cargo
    -0.06
    fire
    -0.06
    POSITIVE LOGITS
    のような
    0.07
    etroit
    0.06
    .city
    0.06
     populated
    0.06
    ütün
    0.06
     کرد
    0.06
    izard
    0.05
     süre
    0.05
     length
    0.05
    .reload
    0.05
    Act Density 0.022%

    No Known Activations