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

    Neuronpedia

    INDEX
    Explanations

    import axios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    deh
    0.40
     RIP
    0.39
     endpoint
    0.39
    ទៀ
    0.39
     thanksgiving
    0.38
    RIP
    0.37
    accouchement
    0.37
     लढ
    0.37
    gateway
    0.37
    HIT
    0.37
    POSITIVE LOGITS
    instance
    0.43
    インスタ
    0.42
    Plans
    0.41
    Instance
    0.38
     चरण
    0.38
    Priv
    0.38
     creando
    0.38
    plans
    0.37
     =>
    0.37
    ීය
    0.36
    Act Density 0.000%

    No Known Activations