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

    Neuronpedia

    INDEX
    Explanations

    ground level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     médicament
    0.40
    倩
    0.40
    jabi
    0.40
    萫
    0.40
    ക്കാരി
    0.39
     backdoor
    0.38
    icist
    0.38
     organisasi
    0.37
     harassing
    0.37
     toJson
    0.37
    POSITIVE LOGITS
     ground
    1.85
    地面
    1.84
    ground
    1.59
     زمین
    1.55
     floor
    1.53
    Ground
    1.52
     GROUND
    1.43
     Ground
    1.41
     suelo
    1.36
    floor
    1.33
    Act Density 0.096%

    No Known Activations