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

    Neuronpedia

    INDEX
    Explanations

    Heart measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compact
    -0.07
    .lists
    -0.07
     다운
    -0.07
    .getPath
    -0.07
    誤
    -0.06
    ouched
    -0.06
     bestowed
    -0.06
     communic
    -0.06
    .bottom
    -0.06
     Protocol
    -0.06
    POSITIVE LOGITS
     нер
    0.07
    ##_
    0.06
    �
    0.06
    ajaran
    0.06
    �
    0.06
    ablish
    0.06
     вив
    0.06
    وير
    0.06
    addField
    0.06
    يت
    0.06
    Act Density 0.023%

    No Known Activations