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

    Neuronpedia

    INDEX
    Explanations

    Java Virtual concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eater
    0.78
    럭
    0.72
    erder
    0.68
    NotBlank
    0.67
     ১০০
    0.66
    嬂
    0.61
     eaters
    0.60
     sk
    0.60
    享受
    0.59
    保険
    0.58
    POSITIVE LOGITS
     Virt
    0.87
     Enh
    0.82
     Viral
    0.79
     VM
    0.76
     Dash
    0.76
     Enhanced
    0.75
     virt
    0.74
    Virt
    0.71
    jha
    0.70
    стви
    0.68
    Act Density 0.015%

    No Known Activations