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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    592
    -0.07
     termination
    -0.07
     Speed
    -0.06
     cruis
    -0.06
    前に
    -0.06
     andere
    -0.06
     inserted
    -0.06
    .animation
    -0.06
    kenin
    -0.06
     stuck
    -0.06
    POSITIVE LOGITS
     ENC
    0.07
    族自治
    0.07
    quiet
    0.07
    はない
    0.06
    ISMATCH
    0.06
    ={()
    0.06
    .oc
    0.06
    casts
    0.06
    istrov
    0.06
    �
    0.06
    Act Density 0.008%

    No Known Activations